Model-Free Monte Carlo-like Policy Evaluation.

Raphael Fonteneau Susan A. Murphy Louis Wehenkel Damien Ernst

Published in: AISTATS (2010)

Keyphrases

policy evaluation
monte carlo
model free
matrix inversion
temporal difference
markov chain
policy iteration
reinforcement learning
importance sampling
variance reduction
function approximation
particle filter
reinforcement learning algorithms
feature selection
data mining
neural network
least squares